total 28took 0.03s

Second Croatian Computer Vision Workshop (CCVW 2013)Oct 01 2013Nov 03 2013Proceedings of the Second Croatian Computer Vision Workshop (CCVW 2013, http://www.fer.unizg.hr/crv/ccvw2013) held September 19, 2013, in Zagreb, Croatia. Workshop was organized by the Center of Excellence for Computer Vision of the University of Zagreb. ... More

Classifying Traffic Scenes Using The GIST Image DescriptorOct 01 2013This paper investigates classification of traffic scenes in a very low bandwidth scenario, where an image should be coded by a small number of features. We introduce a novel dataset, called the FM1 dataset, consisting of 5615 images of eight different ... More

Efficient Ladder-style DenseNets for Semantic Segmentation of Large ImagesMay 14 2019Recent progress of deep image classification models has provided great potential to improve state-of-the-art performance in related computer vision tasks. However, the transition to semantic segmentation is hampered by strict memory limitations of contemporary ... More

A Novel Georeferenced Dataset for Stereo Visual OdometryOct 01 2013In this work, we present a novel dataset for assessing the accuracy of stereo visual odometry. The dataset has been acquired by a small-baseline stereo rig mounted on the top of a moving car. The groundtruth is supplied by a consumer grade GPS device ... More

In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving ImagesMar 20 2019Apr 12 2019Recent success of semantic segmentation approaches on demanding road driving datasets has spurred interest in many related application fields. Many of these applications involve real-time prediction on mobile platforms such as cars, drones and various ... More

In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving ImagesMar 20 2019Recent success of semantic segmentation approaches on demanding road driving datasets has spurred interest in many related application fields. Many of these applications involve real-time prediction on mobile platforms such as cars, drones and various ... More

Combining Spatio-Temporal Appearance Descriptors and Optical Flow for Human Action Recognition in Video DataOct 01 2013This paper proposes combining spatio-temporal appearance (STA) descriptors with optical flow for human action recognition. The STA descriptors are local histogram-based descriptors of space-time, suitable for building a partial representation of arbitrary ... More

Discriminative out-of-distribution detection for semantic segmentationAug 23 2018Oct 01 2018Most classification and segmentation datasets assume a closed-world scenario in which predictions are expressed as distribution over a predetermined set of visual classes. However, such assumption implies unavoidable and often unnoticeable failures in ... More

Pedestrian Tracking by Probabilistic Data Association and Correspondence EmbeddingsJul 16 2019This paper studies the interplay between kinematics (position and velocity) and appearance cues for establishing correspondences in multi-target pedestrian tracking. We investigate tracking-by-detection approaches based on a deep learning detector, joint ... More

Simultaneous Semantic Segmentation and Outlier Detection in Presence of Domain ShiftAug 03 2019Recent success on realistic road driving datasets has increased interest in exploring robust performance in real-world applications. One of the major unsolved problems is to identify image content which can not be reliably recognized with a given inference ... More

Single Level Feature-to-Feature Forecasting with Deformable ConvolutionsJul 26 2019Future anticipation is of vital importance in autonomous driving and other decision-making systems. We present a method to anticipate semantic segmentation of future frames in driving scenarios based on feature-to-feature forecasting. Our method is based ... More

Robust Semantic Segmentation with Ladder-DenseNet ModelsJun 09 2018We present semantic segmentation experiments with a model capable to perform predictions on four benchmark datasets: Cityscapes, ScanNet, WildDash and KITTI. We employ a ladder-style convolutional architecture featuring a modified DenseNet-169 model in ... More

Box counting dimensions of generalised fractal nestsFeb 02 2018Fractal nests are sets defined as unions of unit $n$-spheres scaled by a sequence of $k^{-\alpha}$ for some $\alpha>0$. In this article we generalise the concept to subsets of such spheres and find the formulas for their box counting dimensions. We introduce ... More

The Aubry-Mather theorem for driven generalized elastic chainsMay 06 2013We consider uniformly (DC) or periodically (AC) driven generalized infinite elastic chains (a generalized Frenkel-Kontorova model) with gradient dynamics. We first show that the union of supports of all the invariant measures, denoted by A, projects injectively ... More

Towards semantic and affective coupling in emotionally annotated databasesDec 01 2012Emotionally annotated databases are repositories of multimedia documents with annotated affective content that elicit emotional responses in exposed human subjects. They are primarily used in research of human emotions, attention and development of stress-related ... More

A First-Order Logic for Reasoning about Knowledge and ProbabilityJan 21 2019We present a first-order probabilistic epistemic logic, which allows combining operators of knowledge and probability within a group of possibly infinitely many agents. The proposed framework is the first order extension of the logic of Fagin and Halpern ... More

Hyperplane mass equipartition problem and the shielding functions of RamosAug 06 2015Mar 09 2016We give a proof of the result of Edgar Ramos which claims that two finite, continuous Borel measures $\mu_1$ and $\mu_2$ defined on $\mathbb{R}^5$ admit an equipartition by a collection of three hyperplanes. Our proof illuminates one of the central methods ... More

Multimedia stimuli databases usage patterns: a survey reportMar 20 2013Jan 10 2014Multimedia documents such as images, sounds or videos can be used to elicit emotional responses in exposed human subjects. These stimuli are stored in affective multimedia databases and successfully used for a wide variety of research in affective computing, ... More

Local chromatic number and distinguishing the strength of topological obstructionsFeb 22 2005Apr 19 2007The local chromatic number of a graph G is the number of colors appearing in the most colorful closed neighborhood of a vertex minimized over all proper colorings of G. We show that two specific topological obstructions that have the same implications ... More

Symmetric multiple chessboard complexes and a new theorem of Tverberg typeFeb 18 2015Aug 14 2016We prove a new theorem of Tverberg type which confirms the conjecture of Blagojevic, Frick, and Ziegler about the existence of "balanced Tverberg partitions" (Conjecture 6.6 in, Tverberg plus constraints, Bull. London Math. Soc., 46 (2014) 953-967). The ... More

Topology and combinatorics of 'unavoidable complexes'Mar 28 2016The partition number $\pi(K)$ of a simplicial complex $K\subset 2^{[m]}$ is the minimum integer $\nu$ such that for each partition $A_1\uplus\ldots\uplus A_\nu = [m]$ of $[m]$ at least one of the sets $A_i$ is in $K$. A complex $K$ is $r$-unavoidable ... More

Multiple chessboard complexes and the colored Tverberg problemDec 01 2014Oct 19 2015Following D.B. Karaguezian, V. Reiner, and M.L. Wachs (Matching Complexes, Bounded Degree Graph Complexes, and Weight Spaces of $GL$-Complexes, Journal of Algebra 2001) we study the connectivity degree and shellability of multiple chessboard complexes. ... More

Introducing languid particle dynamics to a selection of PSO variantsJun 06 2019Previous research showed that conditioning a PSO agent's movement based on its personal fitness improvement enhances the standard PSO method. In this article, languid particle dynamics (LPD) technique is used on five adequate and widely used PSO variants. ... More

Topology of unavoidable complexesMar 28 2016Sep 16 2018The partition number $\pi(K)$ of a simplicial complex $K\subset 2^{[m]}$ is the minimum integer $\nu$ such that for each partition $A_1\uplus\ldots\uplus A_\nu = [m]$ of $[m]$ at least one of the sets $A_i$ is in $K$. A complex $K$ is $r$-unavoidable ... More

Combinatorics of `unavoidable complexes'Dec 30 2016The partition number $\pi(K)$ of a simplicial complex $K\subset 2^{[n]}$ is the minimum integer $\nu$ such that for each partition $A_1\uplus\ldots\uplus A_\nu = [n]$ of $[n]$ at least one of the sets $A_i$ is in $K$. A complex $K$ is $r$-unavoidable ... More

On the need for a nonlinear subscale turbulence term in POD models as exemplified for a high Reynolds number flow over an Ahmed bodyOct 23 2013Feb 21 2014We investigate a hierarchy of eddy-viscosity terms in POD Galerkin models to account for a large fraction of unresolved fluctuation energy. These Galerkin methods are applied to Large Eddy Simulation data for a flow around the vehicle-like bluff body ... More

Combinatorics of `unavoidable complexes'Dec 30 2016May 13 2019The partition number $\pi(K)$ of a simplicial complex $K\subset 2^{[n]}$ is the minimum integer $\nu$ such that for each partition $A_1\uplus\ldots\uplus A_\nu = [n]$ of $[n]$ at least one of the sets $A_i$ is in $K$. A complex $K$ is $r$-unavoidable ... More

Cluster-based reduced-order modelling of a mixing layerSep 02 2013Jun 23 2014We propose a novel cluster-based reduced-order modelling (CROM) strategy of unsteady flows. CROM combines the cluster analysis pioneered in Gunzburger's group (Burkardt et al. 2006) and and transition matrix models introduced in fluid dynamics in Eckhardt's ... More